R Notebook

library(tidyverse)
library(janitor)
library(plotly)

package ‘plotly’ was built under R version 3.6.2Registered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

Attaching package: ‘plotly’

The following object is masked from ‘package:ggplot2’:

    last_plot

The following object is masked from ‘package:stats’:

    filter

The following object is masked from ‘package:graphics’:

    layout

library(lubridate)
library(tsibble)

cancer_incidence <- read_csv("../clean_data/cancer_incidence_scotland.csv")

── Column specification ───────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  health_board = col_character(),
  cancer_site = col_character(),
  sex = col_character(),
  year = col_double(),
  incidences_all_ages = col_double(),
  crude_rate = col_double()
)

scotland <- read_csv("../clean_data/scotland_wide.csv")

── Column specification ───────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  health_board = col_character(),
  cancer_site = col_character(),
  sex = col_character(),
  year = col_double(),
  incidences_all_ages = col_double(),
  crude_rate = col_double()
)

borders <- cancer_incidence %>% 
  filter(health_board == "NHS Borders")

ggplotly(borders %>% 
  filter(cancer_site != "All cancer types",
         sex == "All") %>% 
 ggplot() +
 aes(x = year, y = crude_rate, fill = cancer_site) +
 geom_area(size = 1L) +
 scale_fill_hue() +
 labs(x = "Year", y = "Crude rate", title = "Cancer incidence in the Borders", fill = "Type of cancer") +
 theme_minimal())

borders %>%
 filter(sex %in% "All",
        cancer_site != "All cancer types") %>%
 ggplot() +
 aes(x = year, y = crude_rate, colour = cancer_site) +
 geom_line(size = 1L) +
 geom_smooth(span = 0.75) +
 scale_color_hue() +
   labs(x = "Year", y = "Crude rate", title = "Cancer incidence in the Borders", fill = "Type of cancer")+
 theme_minimal()

nationwide_cancer <- rbind(cancer_incidence, scotland)

ggplotly(nationwide_cancer %>%
 filter(sex %in% "All",
        cancer_site == "All cancer types",
        health_board %in% c("scotland_wide", "NHS Borders")) %>%
 ggplot() +
 aes(x = year, y = crude_rate, colour = health_board) +
 geom_line(size = 1L) +
  geom_smooth(span = 0.75)+
  labs(x = "Year", y = "Crude rate", title = "Cancer incidence in the Borders compared to Scotland wide")+
 scale_color_hue() +
 theme_minimal())

`geom_smooth()` using method = 'loess' and formula 'y ~ x'

cancer_tsibble <- nationwide_cancer %>% 
  as_tsibble(index = year)

Error: A valid tsibble must have distinct rows identified by key and index.
ℹ Please use `duplicates()` to check the duplicated rows.

nationwide_cancer %>% 
  filter(year == 1994) %>% 
  slice_max(crude_rate, n = 10)

nationwide_cancer %>% 
  filter(cancer_site == "All cancer types",
         sex == "All") %>% 
  group_by(year) %>% 
  slice_max(crude_rate, n = 5) %>% 
  ggplot()+
  aes(x = year, y = crude_rate, fill = (health_board == "NHS Borders"))+
  scale_fill_discrete(name = " ", labels = c("Other health boards", "NHS Borders"))+
  labs(x = "Year", y = "Crude rate", title = "Top 5 Health Boards with Highest Incidence of Cancer in Scotland")+
  geom_col()

ggplotly(borders %>% 
  filter(sex != "All",
         cancer_site != "All cancer types") %>% 
    group_by(year, sex) %>% 
  slice_max(crude_rate, n = 3) %>% 
  ggplot()+
  aes(x = year, y = crude_rate, colour = cancer_site)+
  facet_wrap(~ sex)+
   theme(legend.position = "none")+
    labs(x = "Year", y = "Crude rate", title = "Top 3 highest incidences of cancer for men and women over the years")+
  geom_line())

NA